Full MULTIPLE Monitoring Solution
MULTIPLE will develop cost-effective multi-modal monitoring solutions with a breakthrough impact on production quality and efficiency. It will bring cutting-edge organic electronics based sensors, snapshot hyperspectral filters and dual-aperture imaging to deliver cost-effective spectrometers and camera cores in a broad VIS/SWIR range, complemented with cost effective laser-based chemometric sensors in the VNIR & MWIR. On top of these sensors, MULTIPLE will develop novel multimodal monitoring systems that will be IoT native, by combining them with cloud, big data, and deep learning for agile development and orchestration of complex AI-based models to optimize production improving EU manufacturing competitiveness.
MULTIPLE Concept
The technologies incorporated within the MULTIPLE project are based on the following characteristics:
Broadband
Working spectral range of 0.4 – 5.0µm
Multimodal
VIS – Surface and volume geometry definition, spectrally-resolved colorimetric assesssment
SWIR – Hyperspectral estimation of mechanical properties, multi-wave-length high temperature thermography
MWIR – chemical composition estimation
Spectral imaging is an imaging technique that captures and processes multiple narrow band images over a spectral range. It enables detailed analysis and identification of objects as they contain unique information at different wavelengths. There are three main methods of acquiring hyperspectral imaging data: spatial scanning, spectral scanning, and snapshot imaging. Snapshot sensors/cameras collect the entire 3D datacube in a single shot without scanning. As a result, they are free of scanning artefacts, far more robust and compact, and benefit from higher optical efficiency.
The technology used in MULTIPLE is based around five building blocks:
Snapshot VIS/SWIR HSI Cameras
MULTIPLE is developing a dual-aperture HSI broadband camera covering the VIS and SWIR. This system combines two camera cores, one CMOS and one InGaAs, on a single frame. Exploiting a dual aperture approach – one aperture for the visible range and the other for the SWIR range – and embedded capabilities for computational imaging, MULTIPLE will build a new camera capable of snapshot computational imaging in a broad spectral range, from 0.4 to 1.7 µm wavelength. Read more >>>
Laser-based IR analysers
MULTIPLE will develop different types of chemometrics models including neural network models and analytical models for robust estimation of gas concentration ratios of different compounds, including CO/CO2/O2, NOx, and acetone using laser-based IR spectroscopy. Different types and structures of neural networks will be studied and developed in order to reach the optimum structure for the application. Read more >>>
Organic electronics based spectrometers
MULTIPLE is developing cost-effective and versatile spectrometers specifically tailored to the applications in three use cases.
Among others, the developments will provide innovative monolithic detectors based on organic electronics with customised resolution addressing the SWIR spectral band. This was identified as the most insightful spectral range for the application in chocolate production, which is the MULTIPLE use case for the food industry. Read more >>>
Multi-modal monitoring systems
In order to manage the big amount of data from the spectral sensors and to stress the most of their potential, MULTIPLE will develop smart photonic -IoT native- monitoring devices. These edge devices will implement novel real-time processing pipelines based on Deep Learning, enabling processing of high dimensionality data like hyperspectral datacubes for different operations in the manufacturing industrial environment, with minimal engineering intervention. Read more >>>
Cloud & Edge computing platform & services
MULTIPLE will establish an integrated production optimisation framework allowing flexible control of the production line, applying real-time control at specific critical points, as well as monitoring the overall production efficiency providing meaningful information for decision making and feedback to update production models and KPIs. Read more >>>